Volume 14, Issue 2 (9-2017)                   JSDP 2017, 14(2): 3-24 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Maskanati S, Keshavarz A. Online Persian Hand Writing Recognition Using Language Model and Reduction of User Writing Rules. JSDP. 2017; 14 (2) :3-24
URL: http://jsdp.rcisp.ac.ir/article-1-428-en.html
Assitant Professor Persian Gulf University
Abstract:   (1359 Views)

The Joint-up, cursive form of Persian words and immense variety of its scripts, also different figures of Persian letters depending on their sitting positions in the words, have turned the Persian handwritings recognition to an intense challenge. The major obstacle of the most often recognition ways, is their inattention to sentence contexture which causes utilizing of a word with correct appearance within an incorrect sentence, when an input word is misrecognized. Sketching a solution that provides suitable analysis of sentence contexture, requires huge linguistic resources to take place as a fine representative for the chosen language to be recognized. In this article, a new method for online recognition of Persian words is presented which tries to improve recognition process by using the term contexture. In this article, the vocabularies collection of Persian language is divided into two groups. The first category is the vocabulary with all of their sub-words being supported by the database of handwritten subclasses, while these vocabulary form 68.2% of the total vocabulary, and the assumptions being scored at the recognition stage, are members of these vocabularies. The second category is the vocabulary that is not supported by the database. Obviously, if the recognition system does not support this vocabulary, it cannot recognize more than 30 percentages of the language's words. At the recognition stage, the symptoms are detected and a symptom tag is produced. Also, at this stage, using the same label, the vocabulary is also selected as the sign with the input word. (These vocabularies are chosen from those were not supported at the recognition stage). Scoring for hypotheses was done by combining recognition scores and linguistic models. The certain fact in this section is that it is impossible to calculate recognition scores due to the absence of hypothetical subheadings. Therefore, the vocabulary score being recognized in the previous steps, is used. According to the studies, it was concluded that if the word is equivalent to a member's input from a supported vocabulary, even if the result of the recognition is incorrect, in most cases the correct term is in the first four hypotheses. Usually, scores of the first few hypotheses are close to each other, and the other assumptions are far from the correct hypothesis. Since the system operates online, unnecessary computations should be avoided. Therefore, if the number of hypotheses in the recognition section are more than four hypotheses, only the first four hypotheses are calculated for the language model. To calculate the recognition score for new hypotheses, if there are fewer than four hypotheses in the recognition section, the lowest hypothesis score and otherwise the hypothesis score are considered for the recognition score of the new hypotheses. Then, as with previous assumptions, for the new hypotheses, the linguistic score is calculated, and then the final score is obtained for each hypothesis. Finally, the assumption with the highest score is considered as the system output, and the rest of the assumptions are displayed in the output to the user. Experiments show that even in the event of a mistake, the correct word is often presented as a second hypothesis in most cases, and in some cases as a third hypothesis. Also, to reduce the limits and rules that gainers compel to submit. The method demonstrated in this article includes the symptoms and morphemes framework of input handwritten are segregated and the framework of each morpheme with its symptoms is specified at first, then the symptoms of morphemes are specified and based on them a collection of words is being considered as a hypothesis. Each hypothesis is given a score by measuring the similarity to input handwritten and according to taken scores, the likely hypotheses are indicated. Then, this procedure is led to achieve hypotheses more likely by lingual models. To totalize the scores of a hypothesis, for the differences in scale of taken scores, a method of score normalization is being offered. The results demonstrate that by utilizing of a language model with an online system of handwriting recognition, a significant reduction of words recognition error rate is being achieved. In addition to error rate reduction, by taking advantages of this language model, a technique is being offered that can handle the Persian vocabulary recognition entirely. By availing the offered manner, the recognition precision at initial stage of letters level up to 95.9% and so the language model recognition up to 99.3% improved. So, using huge linguistic resources for Persian language and utilizing a language model, can improve the accuracy of recognition. For further work, reinforcement learning algorithm is suggested to adapt the algorithm for users.
 

Full-Text [PDF 8742 kb]   (514 Downloads)    
Type of Study: Research | Subject: Paper
Received: 2015/09/26 | Accepted: 2016/11/6 | Published: 2017/10/21 | ePublished: 2017/10/21

References
1. [1] T. Ebrahimi and B. Z. Dehkordi," Using of factor oriented language model for increase of speech recognition rate," 1st conference on new ideas in computer engineering, Sharekord,2015.
2. [2] F. Nooshabadi, A. Ahmadifard, H. Khosravi," Online persian hand writing recognition using Analytical approach", M.S. Thesis, Shahrood university of technology, 2014.
3. [3] M. Mehralian and K. Fooladi," Online persian hand writing discrete letter recognition based on group and main body detection using SVM", 7th Iranian conference on machine vision and image processing, Tehran, 2011.
4. [4] N. Esmailpour and N. Broomandnia, "Recognition of Persian online sub-words based on fuzzy and structural approach using link list structure", 11th Iranian conference on intelligent systems, 2012. [PMCID]
5. [5] Z. K. Mohassesi, S.A. Ebrahimi and A. Farhoodinezhad," The design of a neuro-fuzzy system with simultaneous training for on line recognizing the Persian sub-words", 8th Symposium on advances in science and technology (computer networks, modelling and system security), Mashahd, 2013.
6. [6] M. Imanian, "Semantic clustering of verbs in Persian language", M.S. thesis, Sharif university of technology, 2012.
7. [7] M. Bahrani, H. Sameti, N. Hafezi, S. Momtazi and H. Movasegh, "The use of the Persian text framework in the production of statistical language models for Persian continuous speech recognition systems", 2nd workshop of Persian language and computer, PP. 92-109, 2006. [PMID]
8. [8] Sh. P. Naeini and M. Khademi, "Persian online handwriting fragmentation using feature extraction", 3rd national conference on computer engineering and information technology, P.P. 266-271, Hamedan, Iran, 2010.
9. [9] S. M. Razavi and E. Kabir, "Online Persian hand writing discrete letter recognition using neural network", 3rd Iranian conference on machine vision and image processing, P.P. 83-89, Tehran, Iran, 2004.
10. [10] S. M. Razavi and E. Kabir, "Online Persian hand writing words recognition by Extensive vocabulary", 5th Iranian conference on machine vision and image processing, Iran, 2008.
11. [11] S. M. Razavi and E. Kabir, "A simple way to recognize online Persian sub-words", Iranian journal of electrical and computer engineering, vol. 2, P.P. 63-72, 2005.
12. [12] S. M. Razavi and E. Kabir, "A database for recognizing Persian online hand writing", Iranian journal of electrical and computer engineering, 6th Iranian conference on intelligent systems, Kerman, Iran, 2004.
13. [13] H. Sajedi, M. Jamzadeh, H. Sameti, B. Babaali "Presentation of a Grouping-Based Approach to Recognition of Persian Separated Letters Using the Hidden Markov Model", 12th International conference of Iranian computer society, Tehran, Iran, 2006.
14. [14] V. Ghods and E. Kabir, "The study of common ways of Persian online hand writing for use in their recognition", Tabriz journal of electrical engineering, Vol. 41, No. 1, P.P. 22-32, 2012.
15. [15] "Persian Language and Literature Academy (Publishing Works)", Persian writing order, 9th edition, 2010.
16. [16] J. Kaboodian, H. S. Moadab and J. Shaikhzadegan, "A word search engine based on the hidden Markov model with unlimited vocabulary to search for spoken documentation in real-world environments", 10th national conference of Iranian computer society, 2004.
17. [17] F. Mirzadeh, "Fuzzy based recognition of words in the Persian hand writing", M.S. Thesis, Sharif university of technology, 2007.
18. [18] "Research papers of Persian OCR", The OCR Research Council of the Persian writing and Language Teams, 2007.
19. [19] M. M. Homayoonpor and A. Salimi Badr, "Determining the boundary and type of syntactic expressions in Persian texts", Signal and data processing, Vol. 10, No. 2, P.P. 69-86, 2013.
20. [20] E. B. Tashk, A. Ahmadifard and H. Khosravi, "A two-step method for recognizing Persian handwritten words using the adaptive blocking of image gradients", Signal and data processing, Vol. 12, No. 3, P.P. 15-29, 2015.
21. [21] R. Deinat, M. Aliahmadi, M. Y. Akhlaghipour and B. Babaali, "Introducing a new information retrieval method applicable for speech recognized texts", Signal and data processing, Vol. 13, No. 4, P.P. 93-108, 2016.
22. [22] C. L. Liu, S. Jaeger, and M. Nakagawa, "Online recognition of Chinese characters: the state-of-the-art", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 2, pp. 198–213, 2004. [DOI:10.1109/TPAMI.2004.1262182] [PMID]
23. [23] D. Jurafsky and J. H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Pearson Prentice Hall, 2009.
24. [24] H. N. Eseen and R. Kneser, "On Structuring Probabilistic Dependencies in Stochastic Language Modeling", Computer, Speech, and Language, vol. 8, pp. 1–38, 1994. [DOI:10.1006/csla.1994.1001]
25. [25] H. Witten and T. C. Bell, "The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression", IEEE Transactions on Information Theory, vol. 37, no. 4, pp. 1085–1094, 1991. [DOI:10.1109/18.87000]
26. [26] M. Bijankhan, "The role of the corpus in writing a grammar: An introduction to a software", Iranian Journal of Linguistics, vol. 19, no. 2, 2004.
27. [27] M. P. Harper, L. H. Jamieson, C. D. Mitchell, G. Ying, S. Potisuk, P. N. Srinivasan, R. Chen, C. B. Zoltowski, L. L. McPheters, and B. Pellom, "Integrating language models with speech recognition". AAAI-94 Workshop on the Integration of Natural Language and Speech Processing, Seattle, Washington, pp. 139-146, 1994.
28. [28] R. Plamondon and S. Srihari, "Online and off-line handwriting recognition: a comprehensive survey", Pattern Analysis and Machine, vol. 22, no. 1, pp. 63–84, 2000. [DOI:10.1109/34.824821]
29. [29] S. Al-Emami and M. Usher, "On-line recognition of handwritten Arabic characters", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 704–710, 1990. [DOI:10.1109/34.56214]
30. [30] S. Atkins, J. Clear, and N. Ostler, "Corpus design criteria", Literary and linguistic computing, vol. 7, no. 1, pp. 1–16, 1992. [DOI:10.1093/llc/7.1.1]
31. [31] S. Connell and A. Jain, "Online handwriting recognition using multiple pattern class models", Michigan State University, 2000.
32. [32] S. Jaeger, C. L. Liu, and M. Nakagawa, "The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition", International Journal on Document Analysis and Recognition, vol. 6, no. 2, pp. 75–88, 2003. [DOI:10.1007/s10032-003-0107-y]
33. [33] S. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer", IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 35, no. 3, pp. 400–401, 1987. [DOI:10.1109/TASSP.1987.1165125]

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author


© 2015 All Rights Reserved | Signal and Data Processing